CN114078603A - Intelligent endowment monitoring system and method, computer equipment and readable storage medium - Google Patents
Intelligent endowment monitoring system and method, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN114078603A CN114078603A CN202010809195.XA CN202010809195A CN114078603A CN 114078603 A CN114078603 A CN 114078603A CN 202010809195 A CN202010809195 A CN 202010809195A CN 114078603 A CN114078603 A CN 114078603A
- Authority
- CN
- China
- Prior art keywords
- human body
- early warning
- monitoring
- information
- warning information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 212
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000004458 analytical method Methods 0.000 claims abstract description 51
- 230000000474 nursing effect Effects 0.000 claims abstract description 14
- 230000006399 behavior Effects 0.000 claims description 75
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000001514 detection method Methods 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 16
- 230000009471 action Effects 0.000 claims description 14
- 230000033001 locomotion Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 230000036760 body temperature Effects 0.000 claims description 8
- 238000000586 desensitisation Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000001931 thermography Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 210000001513 elbow Anatomy 0.000 description 1
- 210000002310 elbow joint Anatomy 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 210000003739 neck Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 210000000323 shoulder joint Anatomy 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000011410 subtraction method Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 210000003857 wrist joint Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides an intelligent endowment monitoring system, a method, computer equipment and a readable storage medium, wherein the system comprises: the data acquisition terminal is used for acquiring monitoring information of the nursing and guarding place and transmitting the monitoring information to the processor terminal; the processor terminal is used for detecting the human body in the monitoring information, performing behavior analysis on the human body, and generating danger early warning information of the human body if the human body meets preset early warning rules. The scheme of the invention can solve the problem that the existing intelligent wearable equipment and the old care security monitoring system are not in place in the old care monitoring field.
Description
Technical Field
The invention belongs to the technical field of intelligent monitoring, and particularly relates to an intelligent endowment monitoring system, an intelligent endowment monitoring method, computer equipment, a readable storage medium and an application terminal.
Background
With the development of society and the advancement of aging in China, the problem of old care becomes a civilian problem concerned by the whole society, and the health condition, daily activity monitoring and medical care problems of the old are more and more emphasized. As China is empty, most of the old people are at home and cannot be monitored in time, and accidents of the old people in daily life, such as falling, work and rest disorder, incapability of getting up and the like cannot be found and handled in time. Even in a nursing home with nursing personnel, due to the lack of guardians, the monitoring is difficult under certain specific situations, such as night monitoring, toilets, bathrooms, stairs and the like, and the nursing home is weak in monitoring the old.
Most of the existing endowment health monitoring equipment is wearable detection equipment, a monitoring camera and the like, relevant monitoring data are collected based on the wearable detection equipment, or image information in a room is collected through the monitoring camera, data are transmitted to a data platform through a communication module, and finally monitoring video information, health information and alarm prompt are pushed through a computer application program. In some large-scale mechanisms such as an aged care home, a traditional security monitoring system is basically adopted as a monitoring means at present, namely, a monitoring video is collected by a plurality of monitoring cameras and transmitted to a monitoring room in real time, and then a manual monitoring method is utilized to achieve a monitoring effect.
The existing monitoring device or method has the following defects:
1. the detection precision of the sensing module (such as an acceleration sensing module and a temperature sensing module) of the existing intelligent wearable device for monitoring is not sensitive enough, and meanwhile, the use habit or the action habit (such as arm swinging, elevator taking, riding and the like) of a user has great influence on the detection result, so that the detection result is more inaccurate, even error information occurs, and the accuracy and the user experience of monitoring are seriously influenced by false alarm, and even loss is brought to the user;
2. the existing mainstream intelligent wearable equipment for monitoring comprises an intelligent watch, an intelligent bracelet, an intelligent ring, an intelligent necklace and the like, most of the equipment is complex to operate and complex in wearing process, the learning cost of the old is increased, inconvenience in life is caused, and the situations that the old forgets to take the equipment, is unwilling to take the equipment and even destroys the intelligent wearable equipment are easy to occur;
3. the existing endowment security monitoring system cannot distinguish internal personnel from external personnel, needs watchmen to watch the system day and night, consumes labor cost and is easy to leak;
4. existing devices for elderly care monitoring have difficulty or inconvenience in monitoring private areas, such as bedrooms, bathrooms, etc.
Disclosure of Invention
The invention aims to provide an intelligent endowment monitoring system, an intelligent endowment monitoring method, computer equipment, a readable storage medium and an application terminal, so as to solve one or more technical problems of the existing monitoring equipment. The specific technical scheme is as follows:
in order to achieve the above object, the present invention provides an intelligent care monitoring system, comprising:
the data acquisition terminal is used for acquiring monitoring information of the nursing and guarding place and transmitting the monitoring information to the processor terminal;
the processor terminal is used for detecting the human body in the monitoring information, performing behavior analysis on the human body, and generating danger early warning information of the human body if the human body meets preset early warning rules.
Optionally, the intelligent endowment monitoring system further includes an application terminal for displaying the danger early warning information.
Optionally, in the intelligent endowment monitoring system, the processor terminal detects the human body in the monitoring information by using an image motion detection algorithm.
Optionally, in the intelligent endowment monitoring system, the processor terminal is configured to perform face recognition on the human body, and if the recognized face matches a preset face of the monitored object and it is determined through behavior analysis that the human body has dangerous behaviors, generate dangerous early warning information of the human body; the human body danger early warning information comprises a human face recognition result of the human body and dangerous behaviors of the human body.
Optionally, in the intelligent care monitoring system, the processor terminal is configured to determine that the human face is a stranger, and generate danger early warning information of the human body; the human body danger early warning information comprises a human body face recognition result.
Optionally, in the intelligent care monitoring system, the processor terminal is configured to perform desensitization processing on the monitoring information and send the desensitized monitoring information and the danger early warning information to an application terminal.
Optionally, in the intelligent care monitoring system, the processor terminal is configured to analyze the monitoring information to obtain body temperature information of the human body in the monitoring information.
Optionally, in the intelligent endowment monitoring system, the processor terminal is configured to mark a target object in the monitoring information, where the target object is a human body meeting a preset early warning rule.
Optionally, in the intelligent endowment monitoring system, the processor terminal is configured to combine the marked monitoring information with the risk early warning information to generate a risk early warning event, and store the risk early warning event.
Optionally, in the intelligent endowment monitoring system, when the endowment monitoring place is a private area, the data acquisition terminal includes an infrared camera or a thermal imager;
when the nursing and guarding place is a non-private area, the data acquisition terminal comprises an RGB camera or a depth camera.
Based on the same inventive concept, the invention also provides an intelligent endowment monitoring method, which comprises the following steps:
receiving monitoring information of an aged care monitoring place;
detecting a human body in the monitoring information;
and performing behavior analysis on the human body, and if the human body accords with a preset early warning rule, generating danger early warning information of the human body.
Optionally, in the intelligent endowment monitoring method, the detecting the human body in the monitoring information includes:
and detecting the human body in the monitoring information by adopting an image movement detection algorithm.
Optionally, in the intelligent endowment monitoring method, the method further includes:
carrying out face recognition on the human body;
if the human body accords with the preset early warning rule, generating the danger early warning information of the human body, wherein the danger early warning information comprises the following steps:
if the recognized human face is matched with a preset human face of the monitored object and the human body is determined to have dangerous actions through behavior analysis, generating dangerous early warning information of the human body; the human body danger early warning information comprises a human body face recognition result and human body danger actions.
Optionally, in the intelligent endowment monitoring method, if the human body meets a preset early warning rule, generating danger early warning information of the human body includes:
if the recognized human face is a stranger, generating danger early warning information of the human body; the human body danger early warning information comprises a human body face recognition result.
Optionally, in the intelligent endowment monitoring method, the method further includes:
desensitizing the monitoring information and sending the desensitized monitoring information and the danger early warning information to an application terminal.
Optionally, in the intelligent endowment monitoring method, the method further includes:
and analyzing the monitoring information to acquire the body temperature information of the human body in the monitoring information.
Optionally, in the intelligent endowment monitoring method, the method further includes:
and marking a target object in the monitoring information, wherein the target object is a human body which accords with a preset early warning rule.
Optionally, in the intelligent endowment monitoring method, the method further includes:
and combining the marked monitoring information with the danger early warning information to generate a danger early warning event, and storing the danger early warning event.
Optionally, in the intelligent endowment monitoring method, when the endowment monitoring place is a private area, the data acquisition terminal includes an infrared camera or a thermal imager;
when the nursing and monitoring place is a public area, the data acquisition terminal comprises an RGB camera or a depth camera.
Based on the same inventive concept, the present invention further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the intelligent endowment monitoring method as described above when executing the computer program.
Based on the same inventive concept, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the intelligent endowment monitoring method as described above.
Based on the same inventive concept, the invention further provides an application terminal, which is characterized in that the application terminal comprises a controller and a display, wherein the controller is used for indicating the display to display the danger early warning information, and the danger early warning information is obtained by analyzing the behavior of a human body in the monitoring information of the monitoring place.
Compared with the prior art, the intelligent endowment monitoring system, the intelligent endowment monitoring method, the computer equipment, the readable storage medium and the application terminal have the following beneficial effects: the monitoring information of the monitoring place is acquired through the data acquisition terminal, then the processor terminal carries out human body detection and behavior analysis on the monitoring information, and if the human body accords with preset early warning rules, the danger early warning information of the human body is displayed through the application terminal. Therefore, the life state of the old is intelligently analyzed by using a computer vision technology, the old care monitoring is carried out without depending on intelligent wearable equipment, the condition of inaccurate monitoring cannot occur, the learning cost of the old is not increased, and the problems that the old is unwilling to wear and forgets to wear are solved; the functions of detecting abnormal behaviors, detecting dangers, prompting terminals, intelligently early warning and the like of the old can be realized, the operation, the maintenance and the management are easy, and compared with the existing endowment security monitoring system, the system reduces the manual attendance and reduces the labor cost; the behavior analysis is triggered when a human body is detected, and the analysis cannot be carried out all the time under the condition that a monitoring video picture is unmanned, so that system resources are saved; in addition, the intelligent endowment monitoring system can be flexibly deployed in local or cloud service, is convenient to be compatible with other applications, and has strong expandability.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an intelligent endowment monitoring system according to an embodiment of the present invention;
FIG. 2 is a flowchart of the operation of the intelligent endowment monitoring system shown in FIG. 1;
FIG. 3 is another flow chart of the intelligent endowment monitoring system shown in FIG. 1;
fig. 4 is a schematic flow chart of an intelligent endowment monitoring method according to an embodiment of the present invention;
Detailed Description
The intelligent endowment monitoring system, method, computer device, readable storage medium and application terminal provided by the invention are further described in detail with reference to the accompanying drawings and the detailed description. The advantages and features of the present invention will become more apparent from the following description. It is to be noted that the drawings are in a very simplified form and are all used in a non-precise scale for the purpose of facilitating and distinctly aiding in the description of the embodiments of the present invention. To make the objects, features and advantages of the present invention comprehensible, reference is made to the accompanying drawings. It should be understood that the structures, ratios, sizes, and the like shown in the drawings and described in the specification are only used for matching with the disclosure of the specification, so as to be understood and read by those skilled in the art, and are not used to limit the implementation conditions of the present invention, so that the present invention has no technical significance, and any structural modification, ratio relationship change or size adjustment should still fall within the scope of the present invention without affecting the efficacy and the achievable purpose of the present invention.
The core idea of the invention is to provide an intelligent endowment monitoring system, an intelligent endowment monitoring method, a computer device, a readable storage medium and an application terminal, so as to solve the problem that the existing intelligent wearable device and an endowment security monitoring system are not in place for monitoring in the field of endowment monitoring. The invention adopts the computer vision technology to intelligently analyze the life state of the old people so as to realize better intelligent nursing care. First, a brief description of computer vision techniques is provided below.
The computer vision technology adopts various imaging systems to replace visual organs as input sensitive means, and a computer replaces a brain to complete processing and interpretation. The ultimate research goal of computer vision is to enable a computer to visually observe and understand the world like a human, and have the capability of self-adapting to the environment, such as face recognition, human behavior analysis.
The face recognition technology is to detect the face in the image, extract the characteristic information (such as face contour, five sense organs and position relation) and convert it into data with specific format, then compare the 'face' with the existing face information in the database by the characteristic model to obtain the similarity, thus judging the person.
Human behavior analysis is to let a computer understand the behavior and actions of a person in a viewed picture. The existing human body behavior analysis is performed according to the time-space characteristics of a human body in an image, generally features related to actions such as running, sitting, falling, jumping, waving and the like, and the accuracy rate and the application range of the behavior analysis can be further improved by deep learning.
The basic principle of behavior analysis by using artificial intelligence is as follows: the model is constructed by utilizing artificial intelligence technologies such as deep learning, a large amount of calibration data is used for training the model, for example, the model is made to know that the behavior meeting the standard is determined as behavior A, the behavior meeting another standard is determined as behavior B, and the like, and the precision and the adaptability (robustness) of the model are greatly improved. In a specific behavior analysis application scenario, the models can make specific judgment according to the input new data, for example, behaviors such as running and sitting are automatically recognized, and the purpose of automatic recognition is achieved. The main characteristics adopted in the human behavior analysis are as follows: human behavior recognition features based on a skeleton, a spatial descriptor, time series features, space-time series features, bag of words; the basic algorithms used are: a Long Short-Term Memory (LSTM) network Model, a Support Vector Machine (SVM), a Hidden Markov Model (HMM), an R-CNN algorithm and a Fast R-CNN algorithm.
The principle of the behavior analysis process is illustrated below by taking an ST-GCN (space-time graph convolutional network model, model based on deep learning and artificial intelligence) algorithm based on a skeleton model as an example:
1. performing image preprocessing on data (video frames), including image cropping, image denoising, image enhancement and the like;
2. obtaining 1-2 human bodies with highest human body confidence coefficient (most probably human) in the video frame, and identifying the human bodies by combining a human face matching result;
3. obtaining key nodes of a human body by using a human body key point algorithm, wherein the key nodes are generally 18 joint points (18 such as elbows, knees, necks and the like), describing human body actions as vectors of joint point information of a space skeleton on a time axis, and generating matrix information comprising the joint point information, the number of people and the number of key frames through normalization processing;
4. different joint points belong to different human body parts, and the joint point information is decomposed according to different human body parts, such as: decomposing a left shoulder joint, a left elbow joint and a left wrist joint into a left upper limb, and decomposing original data into a plurality of associated subsets;
5. the convolutional neural network is used for classifying the motion labels for multiple times in a time domain and a space domain, the probability value of each motion label is finally obtained, and the classification result of the motion, such as running, sitting, falling and the like, is predicted according to the probability value.
The intelligent endowment monitoring system provided by the invention is introduced below. Referring to fig. 1, the intelligent endowment monitoring system provided by the present application includes a data acquisition terminal 100, a processor terminal 200 and an application terminal 300.
The data acquisition terminal 100 is configured to acquire monitoring information of an elderly care location and transmit the monitoring information to the processor terminal 200;
the processor terminal 200 is configured to detect a human body in the monitoring information, perform behavior analysis on the human body, and generate danger early warning information of the human body if the human body meets a preset early warning rule;
the processor terminal 200 may push the human body danger early warning information to the application terminal 300, and the application terminal 300 is configured to display the danger early warning information.
The intelligent endowment monitoring system provided by the invention collects the monitoring information of a monitoring place through the data collecting terminal 100, then carries out human body detection and behavior analysis on the monitoring information through the processor terminal 200, and displays the danger early warning information of the human body through the application terminal 300 if the human body accords with the preset early warning rule. Therefore, the behavior and the living state of the old are intelligently analyzed by using a computer vision technology, the old care monitoring is carried out without depending on intelligent wearable equipment, the condition of inaccurate monitoring is avoided, the learning cost of the old is not increased, and the problems that the old is unwilling to wear and forgets to wear are solved; the invention can also realize the functions of abnormal behavior detection, danger detection, terminal prompt, intelligent early warning and the like of the old, is easy to operate, maintain and manage, reduces the manual attendance and reduces the labor cost compared with the existing endowment security monitoring system; the behavior analysis is carried out when a human body is detected, and the analysis can not be carried out all the time under the condition that a monitoring video picture is unmanned, so that system resources are saved; in addition, the intelligent endowment monitoring system can be flexibly deployed in local or cloud service, is convenient to be compatible with other applications, and has strong expandability.
Specifically, the data acquisition terminal 100 is a device for acquiring one or more of non-contact video information, thermal imaging information, and depth image information in real time, such as an RGB camera, a depth camera, an infrared camera, a thermal imager, and the like, and may be disposed in an aged care and care place such as a corridor, a room, a toilet, a public area, and the like, and different data acquisition terminals 100 may be disposed according to different light environments and privacy requirements.
Preferably, when the nursing and care place is a private area, the data acquisition terminal 100 may include an infrared camera or a thermal imager; when the nursing home is a non-private area, the data acquisition terminal 100 may include a high-definition camera such as an RGB camera or a depth camera. The appropriate data acquisition terminal 100 is selected according to different occasions to adapt to different monitoring scenes, and the problem that a traditional endowment security monitoring system is difficult to monitor private areas such as toilets, bedrooms and bathrooms can be solved.
The processor terminal 200 includes a server and an algorithm module. After the monitoring information, such as the monitoring video, transmitted by the data acquisition terminal 100 is acquired, it is preferable that the monitoring video is subjected to image preprocessing, which is a data form convenient for computer vision identification and analysis, and the preprocessing mode includes graying, image denoising, image enhancement, image segmentation, edge detection, and the like.
And then detecting a human body from the processed monitoring video, specifically detecting the human body in the monitoring video by adopting an image motion detection algorithm, wherein the image motion detection algorithm mainly comprises a background subtraction method, an inter-frame difference method and an optical flow method, and the human body is detected by identifying a moving object in an image.
After one or more human bodies are detected, performing behavior analysis on each human body respectively, specifically: the specific behaviors of the human body, such as charging, loitering, falling, sitting, standing, running, etc., are analyzed based on computer vision and deep learning algorithms. The main algorithms for behavior analysis are a behavior analysis algorithm based on skeletal nodes, a behavior analysis algorithm based on spatial features, a behavior analysis algorithm based on temporal features, and the like. The invention mainly adopts a behavior analysis algorithm based on skeleton nodes so as to analyze the monitoring video of a private area, but the private information of a human body is not exposed.
After the human body is subjected to behavior analysis to obtain the specific behavior of each human body, whether the behavior of the human body accords with a preset early warning rule or not is judged, and if the behavior of the human body accords with the preset early warning rule, danger early warning information needs to be sent out. For example, the preset early warning rule may be set to require early warning when the behavior of the human body is judged to belong to one of the behaviors of charging, falling, and the like, and thus, when the behavior of a certain human body meets any one of the above early warning rules, the danger early warning information of the human body needs to be sent out. Of course, the preset early warning rule may be set according to actual conditions, which is not limited in the present invention.
Preferably, the processor terminal may further perform face recognition on each of the human bodies, and if the recognized face matches a preset face of the monitored object and it is determined through behavior analysis that the human body has a dangerous behavior, generate dangerous early warning information of the human body and push the dangerous early warning information to the application terminal 300, where the dangerous early warning information of the human body includes a face recognition result of the human body and a dangerous action of the human body. The identity information of a human body in the monitoring video can be determined through face recognition, if the recognized face is matched with the face of a preset monitored object, the human body is the monitored object, and if the behavior analysis result also shows that dangerous behaviors exist in the human body at the moment, dangerous early warning information needs to be sent out to inform a guardian that the monitored object has dangerous behaviors, and the dangerous behaviors need to be processed in time. The danger warning information may include a face recognition result of the human body, that is, identity information representing the monitored object, such as a name of the monitored object, and dangerous behaviors of the human body. In other embodiments, the danger early warning information may further include information on a current location of the human body, information on a body temperature, and the like.
In addition, in the security system for nursing and monitoring the aged, if the recognized face is a stranger, the danger early warning information of the human body needs to be generated and pushed to the application terminal 300, and the danger early warning information of the human body includes the face recognition result of the human body. For example, if the recognized face is a stranger, a danger warning message needs to be sent out at this time to inform a guardian that a stranger enters, and the stranger needs to be handled in time. The danger early warning information may include a face recognition result of the human body, and in other embodiments, the danger early warning information may further include a behavior analysis result of the human body, information of a current position of the human body, and the like.
In practical application, the default face image of the monitored object can be stored in a database, and when face recognition is performed, the face in the monitoring video is matched with the default face image in the database one by one so as to judge whether the face in the monitoring video is matched with the face of the monitored object. It can be understood that more accurate monitoring of the monitored object can be realized by combining behavior analysis and face recognition.
Further, the processor terminal 200 may further mark a target object in the surveillance video, and push the marked surveillance video to the application terminal 300, where the target object is a human body meeting a preset early warning rule. Namely, after detecting that there is a human body meeting the preset early warning rule in the monitoring video, the human body is marked in the monitoring video, and the marked monitoring video is pushed to the application terminal 300, so that the guardian can more visually see the current dangerous state of the person under guardianship. Further, the processor terminal 200 may further combine the marked surveillance video with the danger early warning information to generate a danger early warning event, and store the danger early warning event.
In addition to the above-mentioned functions of motion detection, behavior analysis, and face recognition, the processor terminal 200 may perform desensitization processing on the surveillance video, perform data deformation on some sensitive information related to personal privacy through a desensitization rule, and implement reliable protection of sensitive privacy data, for example, block a face in the surveillance video, retain human skeleton nodes extracted during behavior analysis, retain a thermal imaging graph, and perform background blurring, and the processor terminal 200 may further send the surveillance video after desensitization processing and the danger early warning information to the application terminal 300. The processor terminal 200 may further implement a body temperature analysis function, that is, perform data analysis on the monitoring video to obtain body temperature information of a human body in the monitoring video, and monitor the health status of the monitored object better by combining the body temperature information.
The application terminal 300 may include a software client, a mobile app, and the like, and is configured to view a monitoring video, receive and display the risk early warning information, and may further be configured with functions of one-key alarm, statistical analysis, system management, and the like.
The key point of the invention is to combine the behavior analysis technology with the endowment monitoring technology to monitor the living condition of the monitored object in real time. Specifically, to data acquisition terminal, select suitable equipment according to the occasion of difference, if use thermal imager, use high definition digtal camera in public area in private spaces such as bathroom, solve the problem that current endowment security protection monitoring system is difficult to the control in private place. The processor terminal applies technologies such as face recognition, behavior analysis and data desensitization, and can monitor the monitored object in real time under the condition of ensuring that the personal privacy is effectively protected. The face recognition and behavior analysis require high accuracy and robustness, so that accurate analysis and early warning can be developed under different scene conditions, and missing report and false report are reduced. In addition, because the living privacy of users and old people is involved, the invention uses data desensitization, encrypted storage and the like to protect the data security and privacy.
Referring to fig. 2, a schematic diagram shows a workflow of the intelligent care monitoring system according to the present invention, which includes the following steps:
1. the data acquisition terminal 100 is arranged at a proper position of the nursing and care place, and is used for acquiring one or more data of RGB (red, green and blue) images, depth images and thermal imaging data, uploading the acquired data to a local or cloud server of the processor terminal 200 in a wired or wireless communication mode, and realizing the function of viewing monitoring pictures in real time;
2. desensitizing the monitoring video, wherein the alternatives are face shielding, reservation and extraction of human skeleton nodes, reservation of a thermal imaging image, background blurring and the like;
3. preprocessing a monitoring video, continuously detecting whether a moving object (namely a human body) exists in the monitoring video, and if so, performing the following face matching and behavior analysis;
4. detecting the face in the monitoring video, comparing the face with a face database to generate a comparison result, and recording the comparison result;
5. tracking the human body in the monitoring video, and performing behavior analysis on the human body to generate behavior analysis results, such as falling, shoulder charging, loitering, falling, sitting, standing, running and the like;
6. comprehensively judging the face matching information and the behavior analysis result to generate early warning information, specifically, if the detected face exists in a face database and dangerous behavior exists in the face through behavior analysis, generating early warning information, and if the detected face does not exist in the face database, directly generating early warning information, such as strangers-running, Zhang III-falling; if no dangerous behavior exists, no early warning information is generated; further, in other embodiments, as shown in fig. 3, in order to avoid that the human face is away from the monitoring device and the early warning information is directly generated without being detected, for the situation that the detection result after the human face matching is that the human face is not in the database, it is still necessary to combine behavior analysis to determine whether there is a dangerous behavior, if there is a dangerous behavior, the early warning information is generated, and if not, the early warning information is not generated.
7. The early warning information is pushed to an application terminal 300, such as a monitoring center server application or a guardian mobile phone App, alarm information is sent and a monitoring line picture is highlighted, and the person is marked in a monitoring video. The application terminal 300 can also provide options of one-key alarming, one-key calling of a rescue vehicle, early warning releasing, manual handling and the like;
8. combining the early warning information with the monitoring video to generate a dangerous early warning event, and storing the dangerous early warning event in a database;
9. the intelligent endowment monitoring system can also comprise a management function, mainly used for setting the functional parameters and working mode of the system and maintaining the system, and the management function mainly comprises: page management, face recognition database management, event management, algorithm sensitivity setting and the like.
Based on the same inventive concept, the present invention further provides an intelligent endowment monitoring method, which can be specifically applied to a processor terminal, please refer to fig. 4, including:
step S101, receiving monitoring information of an aged care monitoring place;
step S102, detecting a human body in the monitoring information;
step S103, performing behavior analysis on the human body, and if the human body meets preset early warning rules, generating danger early warning information of the human body.
Preferably, in the intelligent care monitoring method, the detecting a human body in the monitoring information includes:
and detecting the human body in the monitoring information by adopting an image movement detection algorithm.
Preferably, in the intelligent care monitoring method, the method further includes:
carrying out face recognition on the human body;
if the human body accords with the preset early warning rule, generating the danger early warning information of the human body, wherein the danger early warning information comprises the following steps:
and if the recognized human face is matched with a preset human face of the monitored object and the human body is determined to have dangerous actions through behavior analysis, generating the dangerous early warning information of the human body, wherein the dangerous early warning information of the human body comprises the human face recognition result of the human body and the dangerous actions of the human body.
Preferably, in the intelligent endowment monitoring method, if the human body meets a preset early warning rule, the method generates the human body danger early warning information, including:
and if the recognized human face is a stranger, generating the human body danger early warning information, wherein the human body danger early warning information comprises the human body face recognition result.
Preferably, in the intelligent care monitoring method, the method includes:
desensitizing the monitoring information and sending the desensitized monitoring information and the danger early warning information to an application terminal.
Preferably, in the intelligent care monitoring method, the method further includes:
and analyzing the monitoring information to acquire the body temperature information of the human body in the monitoring information.
Preferably, in the intelligent care monitoring method, the method further includes:
and marking a target object in the monitoring information, wherein the target object is a human body which accords with a preset early warning rule.
Preferably, in the intelligent care monitoring method, the method further includes:
and combining the marked monitoring information with the danger early warning information to generate a danger early warning event, and storing the danger early warning event.
Preferably, in the intelligent endowment monitoring method, when the endowment monitoring place is a private area, the data acquisition terminal comprises an infrared camera or a thermal imager;
when the nursing and monitoring place is a public area, the data acquisition terminal comprises an RGB camera or a depth camera.
The application scenario of the above embodiment is an endowment monitoring place, and in other embodiments, the monitoring system and the monitoring method described above may also be applied to a security monitoring place.
Based on the same inventive concept, the invention further provides an application terminal, which comprises a controller and a display, wherein the controller is used for indicating the display to display the danger early warning information, and the danger early warning information is obtained by analyzing the human body in the monitoring information of the monitoring place.
Based on the same inventive concept, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements an intelligent endowment monitoring method as described above. The storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Based on the same inventive concept, the present invention also provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the intelligent endowment monitoring method as described above when executing the computer program.
Specifically, in the embodiment of the present invention, the processor may be a Central Processing Unit (CPU), and the processor may also be another general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or another programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will also be appreciated that the memory in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM) which acts as external cache memory. By way of example and not limitation, many forms of Random Access Memory (RAM) are available, such as Static RAM (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (enhanced SDRAM), SDRAM (SLDRAM), synchlink DRAM (SLDRAM), and direct bus RAM (DR RAM).
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only for the purpose of describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.
Claims (17)
1. An intelligent endowment monitoring system, comprising:
the data acquisition terminal is used for acquiring monitoring information of the nursing and guarding place and transmitting the monitoring information to the processor terminal;
the processor terminal is used for detecting the human body in the monitoring information, performing behavior analysis on the human body, and generating danger early warning information of the human body if the human body meets preset early warning rules.
2. The intelligent endowment monitoring system of claim 1, further comprising an application terminal for displaying the danger early warning information.
3. The intelligent endowment monitoring system of claim 1, wherein the processor terminal detects a human body in the monitoring information by using an image motion detection algorithm.
4. The intelligent endowment monitoring system as claimed in claim 1, wherein the processor terminal is configured to perform face recognition on the human body, and if the recognized face matches a preset face of the monitored object and it is determined through behavior analysis that the human body has dangerous behavior, generate dangerous early warning information of the human body; the human body danger early warning information comprises a human face recognition result of the human body and dangerous behaviors of the human body.
5. The intelligent endowment monitoring system of claim 4, wherein the processor terminal is configured to generate danger early warning information of the human body if the identified human face is a stranger; the human body danger early warning information comprises a human body face recognition result.
6. The intelligent endowment monitoring system of claim 1, wherein the processor terminal is configured to perform desensitization processing on the monitoring information and send the desensitized monitoring information and the danger early warning information to an application terminal.
7. The intelligent endowment monitoring system as claimed in claim 1, wherein the processor terminal is configured to analyze the monitoring information to obtain body temperature information of a human body in the monitoring information.
8. The intelligent endowment monitoring system of claim 1, wherein the processor terminal is configured to mark a target object in the monitoring information, wherein the target object is a human body meeting a preset early warning rule.
9. The intelligent endowment monitoring system of claim 8, wherein the processor terminal is configured to combine the marked monitoring information with the dangerous early warning information to generate a dangerous early warning event, and store the dangerous early warning event.
10. An intelligent endowment monitoring method is characterized by comprising the following steps:
receiving monitoring information of an aged care monitoring place;
detecting a human body in the monitoring information;
and performing behavior analysis on the human body, and if the human body accords with a preset early warning rule, generating danger early warning information of the human body.
11. The intelligent endowment monitoring method as claimed in claim 10, wherein the detecting the human body in the monitoring information comprises:
and detecting the human body in the monitoring information by adopting an image movement detection algorithm.
12. The intelligent endowment monitoring method as claimed in claim 10, further comprising:
carrying out face recognition on the human body;
if the human body accords with the preset early warning rule, generating the danger early warning information of the human body, wherein the danger early warning information comprises the following steps:
if the recognized human face is matched with a preset human face of the monitored object and the human body is determined to have dangerous actions through behavior analysis, generating dangerous early warning information of the human body; the human body danger early warning information comprises a human body face recognition result and human body danger actions.
13. The intelligent endowment monitoring method as claimed in claim 12, wherein the generating of the human body danger early warning information if the human body meets a preset early warning rule comprises:
if the recognized human face is a stranger, generating danger early warning information of the human body; the human body danger early warning information comprises a human body face recognition result.
14. The intelligent endowment monitoring method as claimed in claim 10, further comprising:
desensitizing the monitoring information and sending the desensitized monitoring information and the danger early warning information to an application terminal.
15. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 10-14.
16. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 10 to 14.
17. The application terminal is characterized by comprising a controller and a display, wherein the controller is used for indicating the display to display danger early warning information, and the danger early warning information is obtained by analyzing the behaviors of a human body in monitoring information of a monitoring place.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010809195.XA CN114078603A (en) | 2020-08-12 | 2020-08-12 | Intelligent endowment monitoring system and method, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010809195.XA CN114078603A (en) | 2020-08-12 | 2020-08-12 | Intelligent endowment monitoring system and method, computer equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114078603A true CN114078603A (en) | 2022-02-22 |
Family
ID=80280503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010809195.XA Withdrawn CN114078603A (en) | 2020-08-12 | 2020-08-12 | Intelligent endowment monitoring system and method, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114078603A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419528A (en) * | 2022-04-01 | 2022-04-29 | 浙江口碑网络技术有限公司 | Anomaly identification method and device, computer equipment and computer readable storage medium |
| CN114973415A (en) * | 2022-06-02 | 2022-08-30 | 华中科技大学 | Home behavior detection method and system based on double-layer privacy filtering mechanism |
| CN115116133A (en) * | 2022-06-14 | 2022-09-27 | 鹏城实验室 | Abnormal behavior detection system and method for monitoring solitary old people |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130335550A1 (en) * | 2011-02-22 | 2013-12-19 | Flir Systems, Inc. | Infrared sensor systems and methods |
| CN108937952A (en) * | 2018-06-05 | 2018-12-07 | 上海东巍体育科技有限公司 | A kind of the elderly's motion state detection system and method based on thermal imaging |
| CN109360374A (en) * | 2018-12-20 | 2019-02-19 | 湖南晖龙集团股份有限公司 | A kind of falling over of human body automatic early-warning system based on Internet of Things |
| CN110135319A (en) * | 2019-05-09 | 2019-08-16 | 广州大学 | A kind of anomaly detection method and its system |
| CN110781808A (en) * | 2019-10-23 | 2020-02-11 | 泰康保险集团股份有限公司 | Fall detection method, device, equipment and storage medium |
| CN111210592A (en) * | 2020-01-07 | 2020-05-29 | 珠海爬山虎科技有限公司 | Video identification monitoring method, computer device and computer readable storage medium |
| CN111429330A (en) * | 2020-03-31 | 2020-07-17 | 上海兑观信息科技技术有限公司 | Method and system for protecting privacy of monitoring video |
-
2020
- 2020-08-12 CN CN202010809195.XA patent/CN114078603A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130335550A1 (en) * | 2011-02-22 | 2013-12-19 | Flir Systems, Inc. | Infrared sensor systems and methods |
| CN108937952A (en) * | 2018-06-05 | 2018-12-07 | 上海东巍体育科技有限公司 | A kind of the elderly's motion state detection system and method based on thermal imaging |
| CN109360374A (en) * | 2018-12-20 | 2019-02-19 | 湖南晖龙集团股份有限公司 | A kind of falling over of human body automatic early-warning system based on Internet of Things |
| CN110135319A (en) * | 2019-05-09 | 2019-08-16 | 广州大学 | A kind of anomaly detection method and its system |
| CN110781808A (en) * | 2019-10-23 | 2020-02-11 | 泰康保险集团股份有限公司 | Fall detection method, device, equipment and storage medium |
| CN111210592A (en) * | 2020-01-07 | 2020-05-29 | 珠海爬山虎科技有限公司 | Video identification monitoring method, computer device and computer readable storage medium |
| CN111429330A (en) * | 2020-03-31 | 2020-07-17 | 上海兑观信息科技技术有限公司 | Method and system for protecting privacy of monitoring video |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419528A (en) * | 2022-04-01 | 2022-04-29 | 浙江口碑网络技术有限公司 | Anomaly identification method and device, computer equipment and computer readable storage medium |
| CN114973415A (en) * | 2022-06-02 | 2022-08-30 | 华中科技大学 | Home behavior detection method and system based on double-layer privacy filtering mechanism |
| CN114973415B (en) * | 2022-06-02 | 2023-08-18 | 华中科技大学 | Household behavior detection method and system based on double-layer privacy filtering mechanism |
| CN115116133A (en) * | 2022-06-14 | 2022-09-27 | 鹏城实验室 | Abnormal behavior detection system and method for monitoring solitary old people |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Galvão et al. | A multimodal approach using deep learning for fall detection | |
| CN114078603A (en) | Intelligent endowment monitoring system and method, computer equipment and readable storage medium | |
| CN108734055B (en) | Abnormal person detection method, device and system | |
| CN112364696B (en) | Method and system for improving family safety by utilizing family monitoring video | |
| CN112842258A (en) | Methods, processors, and computer-readable media for event prevention and prediction | |
| US11631306B2 (en) | Methods and system for monitoring an environment | |
| Anishchenko | Machine learning in video surveillance for fall detection | |
| US20190167157A1 (en) | Device, system and method for fall detection | |
| US20210364356A1 (en) | System and method for using artificial intelligence to enable elevated temperature detection of persons using commodity-based thermal cameras | |
| KR102233679B1 (en) | Apparatus and method for detecting invader and fire for energy storage system | |
| CN117409538A (en) | Wireless fall-prevention alarm system and method for nursing | |
| KR102157201B1 (en) | System and method for determining disastrous based on image and accident record analysis | |
| Sree et al. | A computer vision based fall detection technique for home surveillance | |
| Yun et al. | A monitoring system to support home health care for the elderly with dementia by detecting going out activities based on RGB-D sensors | |
| JP7210163B2 (en) | Image processing device, image processing method and program | |
| CN115953815A (en) | Monitoring method and device for infrastructure site | |
| Chen et al. | A dynamic height analysis on vision based fall detection system | |
| Silapasuphakornwong et al. | A conceptual framework for an elder-supported smart home | |
| Kutchka et al. | Automatic assessment of environmental hazards for fall prevention using smart-cameras | |
| Abraham et al. | Pro-Safe: An IoT based Smart Application for Emergency Help | |
| Durairaj et al. | AI-driven drowned-detection system for rapid coastal rescue operations | |
| KR20150031059A (en) | The Development Of CCTV For Security By Pattern Recognition Technology | |
| CN110807344A (en) | Special user monitoring method and equipment based on image analysis and storage medium | |
| Daga et al. | Applications of Human Activity Recognition in Different Fields: A Review | |
| KR102662251B1 (en) | Ai-based dementia patient tracking and management method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220222 |